Template-as-Ontology: Configurable Synthetic Data Infrastructure for Cross-Domain Manufacturing AI Validation
Authors: Grama Chethan
Summary
The authors introduce "Template-as-Ontology," a framework where a single Python configuration file defines both a manufacturing simulator and the runtime schema for AI analytics tools, guaranteeing alignment by construction. A five-layer pipeline generates causally coherent, MES-shaped synthetic data across six industry domains (aerospace, pharma, automotive, etc.) mapped to ISA-95 standards. They validate that ontology-constrained tool parameters eliminate hallucination—0% fabricated tool parameters when constrained versus 43% unconstrained for Qwen3-32B—because structural constraints are enforced at the architecture level, not learned.
Main takeaways:
- A single configuration module serves as both the simulator spec and the AI tool schema, ensuring structural alignment automatically.
- Five-layer pipeline produces synthetic manufacturing data spanning 66 entity types across four operational domains.
- Validated on six industry templates running identical framework code; observed KPIs fall within configured ranges.
- Ontology-constrained parameters achieve 0% tool-parameter hallucination versus 43% unconstrained (Fisher's exact test p < 10^-12).
- The 0% hallucination rate is an architectural guarantee from enforced constraints, independent of which model you use.
Relevance
Not directly related to my persona/midtraining work—included because the idea of constraining behavior at the architecture level (rather than relying on training) parallels my interest in installation-path equivalence and whether prompts/steering/fine-tuning achieve the same behavioral constraints.
Abstract
arXiv:2605.11259v1 Announce Type: new Abstract: LLarge language model (LLM)-based AI agents deployed in manufacturing environments require populated, schema-correct data for validation, yet production MES data is proprietary, privacy-encumbered, and vendor-specific. This paper introduces the Template-as-Ontology principle: a single Python configuration module (700-770 lines, 45 validated exports) serves simultaneously as the specification for a time-stepped manufacturing simulator and as the runtime domain schema for AI analytics tools, producing alignment by construction rather than integration. We formally define the domain template as a typed relational configuration schema and prove that structural alignment between simulation and tool layers is guaranteed by single-source consumption. A five-layer pipeline--simulation, PostgreSQL, CDC/Iceberg lakehouse, star schema, and 12 parameterized AI tools--generates causally coherent, MES-shaped data spanning 66 entity types across four operational domains mapped to ISA-95/IEC 62264. We validate the architecture with six industry templates (aerospace, pharma, automotive, electronics, beverages, warehousing) running on identical framework code. Calibration experiments (60 runs, 10 seeds per template) confirm parametric controllability: observed KPIs fall within configured ranges across all templates. A controlled hallucination experiment (72 tool invocations, Qwen3-32B) demonstrates that ontology-constrained parameters eliminate tool-parameter fabrication (0% constrained vs. 43% unconstrained hallucination rate for the evaluated model, Fisher's exact test p < 10^-12); the 0% constrained rate is an architectural guarantee that holds for any model. The framework provides a reusable data layer for discrete manufacturing AI validation.